GABezier at the SBST 2021 Tool Competition

Klück, Florian; Klampfl, Lorenz; Wotawa, Franz

doi:10.1109/sbst52555.2021.00017

Cited by 6 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where Lev dist(i, j) indicates the weighted Levenshtein distance between the road segments. In order to provide a comparative analysis, we compare the results of the proposed test generators in Deeper with the presented test generators in the tool competition, i.e., Frenetic [25], GABExploit and GABExplore [22], Swat [26], and also the earlier version of Deeper [20]. We run the test generators on the test subject based on the same two experiment configurations as in the competition, which are shown in table I.…”

Section: Empirical Evaluationmentioning

confidence: 99%

“…Several authors have shown the potential of search-based software test generation techniques to address this challenge. Various system-level testing techniques using different search-based testing approaches [17]- [22] for different types of ADAS, relying on simulators, have been proposed in recent years.…”

Section: Introductionmentioning

confidence: 99%

“…In order to carry out an empirical evaluation, we use the setup provided by the cyber-physical systems (CPS) testing competition 1 We provide a comparative analysis on the performance of the proposed bio-inspired test generators in Deeper and five counterpart tools all integrated into the BeamNG simulator. In this regard, we compare the results of the proposed test generators in Deeper with five other test generator tools, Frenetic [25], GABExploit and GABExplore [22], Swat [26], and also the earlier version of the Deeper (based on NSGA-II) [20]-all participating tools in the CPS competition at SBST 2021. In order to do a fair comparison, we consider the same experimental evaluation procedures as the original CPS tool competition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testing

Moghadam¹,

Borg²,

Saadatmand³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents an extended version of Deeper, a search-based simulation-integrated test solution that generates failure-revealing test scenarios for testing a deep neural network-based lane-keeping system. In the newly proposed version, we utilize a new set of bio-inspired search algorithms, genetic algorithm (GA), (µ + λ) and (µ, λ) evolution strategies (ES), and particle swarm optimization (PSO), that leverage a quality population seed and domain-specific cross-over and mutation operations tailored for the presentation model used for modeling the test scenarios. In order to demonstrate the capabilities of the new test generators within Deeper, we carry out an empirical evaluation and comparison with regard to the results of five participating tools in the cyber-physical systems testing competition at SBST 2021. Our evaluation shows the newly proposed test generators in Deeper not only represent a considerable improvement on the previous version but also prove to be effective and efficient in provoking a considerable number of diverse failure-revealing test scenarios for testing an ML-driven lane-keeping system. They can trigger several failures while promoting test scenario diversity, under a limited test time budget, high target failure severity, and strict speed limit constraints.

show abstract

Section: Empirical Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testing

Moghadam¹,

Borg²,

Saadatmand³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We provide a comparative analysis on the performance of the proposed bio‐inspired test generators in Deeper and five counterpart tools all integrated into the BeamNG simulator. In this regard, we compare the results of the proposed test generators in Deeper with five other test generator tools, Frenetic, 24 GABExploit and GABExplore, 17 Swat, 25 and also the earlier version of the Deeper (based on NSGA‐II) 15 —all participating tools in the CPS competition at SBST 2021. In order to do a fair comparison, we consider the same experimental evaluation procedures as the original CPS tool competition.…”

Section: Introductionmentioning

confidence: 99%

“…Several authors have shown the potential of search-based software test generation techniques to address this challenge. Various system-level testing techniques using different search-based testing approaches [12][13][14][15][16][17] for different types of ADAS, relying on simulators, have been proposed in recent years.…”

mentioning

confidence: 99%

Machine learning testing in an ADAS case study using simulation‐integrated bio‐inspired search‐based testing

Moghadam

Borg

Saadatmand

et al. 2023

J Software Evolu Process

View full text Add to dashboard Cite

SummaryThis paper presents an extended version of Deeper, a search‐based simulation‐integrated test solution that generates failure‐revealing test scenarios for testing a deep neural network‐based lane‐keeping system. In the newly proposed version, we utilize a new set of bio‐inspired search algorithms, genetic algorithm (GA), and evolution strategies (ES), and particle swarm optimization (PSO), that leverage a quality population seed and domain‐specific crossover and mutation operations tailored for the presentation model used for modeling the test scenarios. In order to demonstrate the capabilities of the new test generators within Deeper, we carry out an empirical evaluation and comparison with regard to the results of five participating tools in the cyber‐physical systems testing competition at SBST 2021. Our evaluation shows the newly proposed test generators in Deeper not only represent a considerable improvement on the previous version but also prove to be effective and efficient in provoking a considerable number of diverse failure‐revealing test scenarios for testing an ML‐driven lane‐keeping system. They can trigger several failures while promoting test scenario diversity, under a limited test time budget, high target failure severity, and strict speed limit constraints.

show abstract